2021 |
|
|
Velesaca, H. O., Suárez, P. L., Mira, R., & Sappa, A.D. (2021). Computer Vision based Food Grain Classification: a Comprehensive Survey. In Computers and Electronics in Agriculture Journal. (Article number 106287), Vol. 187.
|
|
2020 |
|
|
Ángel Morera, Á. S., A. Belén Moreno, Angel D. Sappa, & José F. Vélez. (2020). SSD vs. YOLO for Detection of Outdoor Urban Advertising Panels under Multiple Variabilities. In Sensors, Vol. 2020-August(16), pp. 1–23.
Abstract: This work compares Single Shot MultiBox Detector (SSD) and You Only Look Once (YOLO)
deep neural networks for the outdoor advertisement panel detection problem by handling multiple
and combined variabilities in the scenes. Publicity panel detection in images o ers important
advantages both in the real world as well as in the virtual one. For example, applications like Google
Street View can be used for Internet publicity and when detecting these ads panels in images, it could
be possible to replace the publicity appearing inside the panels by another from a funding company.
In our experiments, both SSD and YOLO detectors have produced acceptable results under variable
sizes of panels, illumination conditions, viewing perspectives, partial occlusion of panels, complex
background and multiple panels in scenes. Due to the diculty of finding annotated images for the
considered problem, we created our own dataset for conducting the experiments. The major strength
of the SSD model was the almost elimination of False Positive (FP) cases, situation that is preferable
when the publicity contained inside the panel is analyzed after detecting them. On the other side,
YOLO produced better panel localization results detecting a higher number of True Positive (TP)
panels with a higher accuracy. Finally, a comparison of the two analyzed object detection models
with di erent types of semantic segmentation networks and using the same evaluation metrics is
also included.
|
|
|
|
Cristhian A. Aguilera, C. A., Cristóbal A. Navarro, & Angel D. Sappa. (2020). Fast CNN Stereo Depth Estimation through Embedded GPU Devices. Sensors 2020, Vol. 2020-June(11), pp. 1–13.
Abstract: Current CNN-based stereo depth estimation models can barely run under real-time
constraints on embedded graphic processing unit (GPU) devices. Moreover, state-of-the-art
evaluations usually do not consider model optimization techniques, being that it is unknown what is
the current potential on embedded GPU devices. In this work, we evaluate two state-of-the-art models
on three different embedded GPU devices, with and without optimization methods, presenting
performance results that illustrate the actual capabilities of embedded GPU devices for stereo depth
estimation. More importantly, based on our evaluation, we propose the use of a U-Net like architecture
for postprocessing the cost-volume, instead of a typical sequence of 3D convolutions, drastically
augmenting the runtime speed of current models. In our experiments, we achieve real-time inference
speed, in the range of 5–32 ms, for 1216 368 input stereo images on the Jetson TX2, Jetson Xavier,
and Jetson Nano embedded devices.
|
|
|
|
Henry O. Velesaca, Raul A. Mira, Patricia L. Suarez, Christian X. Larrea, & Angel D. Sappa. (2020). Deep Learning based Corn Kernel Classification. In The 1st International Workshop and Prize Challenge on Agriculture-Vision: Challenges & Opportunities for Computer Vision in Agriculture on the Conference Computer on Vision and Pattern Recongnition (CVPR 2020) (Vol. 2020-June, pp. 294–302).
Abstract: This paper presents a full pipeline to classify sample sets of corn kernels. The proposed approach follows a segmentation-classification scheme. The image segmentation is performed through a well known deep learning based
approach, the Mask R-CNN architecture, while the classification is performed by means of a novel-lightweight network specially designed for this task—good corn kernel, defective corn kernel and impurity categories are considered.
As a second contribution, a carefully annotated multitouching corn kernel dataset has been generated. This dataset has been used for training the segmentation and
the classification modules. Quantitative evaluations have been performed and comparisons with other approaches provided showing improvements with the proposed pipeline.
|
|
